BCGC-TunnelJoint: A High-Resolution Pixel-Level Dataset for Natural Tunnel Face Joint Segmentation under Blasting–Complex Geological Coupling Conditions
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Lingua: | inglese |
| Pubblicazione: |
Zenodo
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901469702127616 |
|---|---|
| author | Anonymous |
| author_facet | Anonymous |
| contents | <h2>Overview</h2> <p>The <strong>BCGC-TunnelJoint dataset</strong> contains high-resolution images of tunnel faces collected from drilling-blasting tunnel construction sites. The dataset focuses on the segmentation of natural geological joints under complex BCGC environments.</p> <p>Each image is manually annotated at the pixel level to identify joint regions. The dataset is specifically designed to support research on:</p> <ul> <li> <p>Fine-grained tunnel joint segmentation</p> </li> <li> <p>Deep learning–based geological structure detection</p> </li> <li> <p>Robust segmentation under complex construction environments</p> </li> <li> <p>Intelligent monitoring of surrounding rock stability</p> </li> </ul> <h2>Data Characteristics</h2> <p>The dataset captures several important characteristics of tunnel joints under BCGC conditions:</p> <ul> <li> <p>Irregular and discontinuous joint morphology</p> </li> <li> <p>Thin and elongated structural features</p> </li> <li> <p>Severe class imbalance between joint and background pixels</p> </li> <li> <p>Environmental interference including dust, water stains, debris, and uneven illumination</p> </li> </ul> <p>These characteristics make the dataset particularly suitable for evaluating segmentation algorithms in challenging engineering scenarios.</p> <h2>Annotation Method</h2> <p>All images are annotated using <strong>pixel-level semantic segmentation masks</strong>.</p> <p>The annotation process includes:</p> <ol> <li> <p>Manual labeling by trained annotators</p> </li> <li> <p>Cross-validation by multiple experts</p> </li> <li> <p>Consistency checking to ensure labeling quality</p> </li> </ol> <p>Each mask represents the binary segmentation of <strong>joint vs background</strong>.<br><br></p> <blockquote> <p>To ensure data privacy and prevent unintended information leakage, all images were processed to remove embedded EXIF metadata, including GPS coordinates, device information, and timestamps.</p> </blockquote> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18981548 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | BCGC-TunnelJoint: A High-Resolution Pixel-Level Dataset for Natural Tunnel Face Joint Segmentation under Blasting–Complex Geological Coupling Conditions Anonymous Tunnel joint segmentation Tunnel face dataset Blasting excavation Geological structure detection Deep learning segmentation <h2>Overview</h2> <p>The <strong>BCGC-TunnelJoint dataset</strong> contains high-resolution images of tunnel faces collected from drilling-blasting tunnel construction sites. The dataset focuses on the segmentation of natural geological joints under complex BCGC environments.</p> <p>Each image is manually annotated at the pixel level to identify joint regions. The dataset is specifically designed to support research on:</p> <ul> <li> <p>Fine-grained tunnel joint segmentation</p> </li> <li> <p>Deep learning–based geological structure detection</p> </li> <li> <p>Robust segmentation under complex construction environments</p> </li> <li> <p>Intelligent monitoring of surrounding rock stability</p> </li> </ul> <h2>Data Characteristics</h2> <p>The dataset captures several important characteristics of tunnel joints under BCGC conditions:</p> <ul> <li> <p>Irregular and discontinuous joint morphology</p> </li> <li> <p>Thin and elongated structural features</p> </li> <li> <p>Severe class imbalance between joint and background pixels</p> </li> <li> <p>Environmental interference including dust, water stains, debris, and uneven illumination</p> </li> </ul> <p>These characteristics make the dataset particularly suitable for evaluating segmentation algorithms in challenging engineering scenarios.</p> <h2>Annotation Method</h2> <p>All images are annotated using <strong>pixel-level semantic segmentation masks</strong>.</p> <p>The annotation process includes:</p> <ol> <li> <p>Manual labeling by trained annotators</p> </li> <li> <p>Cross-validation by multiple experts</p> </li> <li> <p>Consistency checking to ensure labeling quality</p> </li> </ol> <p>Each mask represents the binary segmentation of <strong>joint vs background</strong>.<br><br></p> <blockquote> <p>To ensure data privacy and prevent unintended information leakage, all images were processed to remove embedded EXIF metadata, including GPS coordinates, device information, and timestamps.</p> </blockquote> |
| title | BCGC-TunnelJoint: A High-Resolution Pixel-Level Dataset for Natural Tunnel Face Joint Segmentation under Blasting–Complex Geological Coupling Conditions |
| topic | Tunnel joint segmentation Tunnel face dataset Blasting excavation Geological structure detection Deep learning segmentation |
| url | https://doi.org/10.5281/zenodo.18981548 |